pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Geometric Scaling of Bayesian Inference in LLMs

cs.LG · 2025-12-27 · unverdicted · novelty 5.0

Large language models preserve a geometric substrate in value representations that correlates with uncertainty and matches patterns from small models performing exact Bayesian inference.

citing papers explorer

Showing 1 of 1 citing paper.

  • Geometric Scaling of Bayesian Inference in LLMs cs.LG · 2025-12-27 · unverdicted · none · ref 8

    Large language models preserve a geometric substrate in value representations that correlates with uncertainty and matches patterns from small models performing exact Bayesian inference.